UA132430U - METHOD OF WORK OF THE SYSTEM OF MAKING COMPLEX DECISIONS BY ARTIFICIAL INTELLIGENCE - Google Patents
METHOD OF WORK OF THE SYSTEM OF MAKING COMPLEX DECISIONS BY ARTIFICIAL INTELLIGENCEInfo
- Publication number
- UA132430U UA132430U UAU201809705U UAU201809705U UA132430U UA 132430 U UA132430 U UA 132430U UA U201809705 U UAU201809705 U UA U201809705U UA U201809705 U UAU201809705 U UA U201809705U UA 132430 U UA132430 U UA 132430U
- Authority
- UA
- Ukraine
- Prior art keywords
- vector
- effect
- information
- learning
- artificial intelligence
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
Abstract
Спосіб роботи системи прийняття складних рішень засобами штучного інтелекту включає процедуру навчання та формування вектора (сигналу) у вигляді кодової послідовності, що являє собою прийняття системою рішення. При цьому системою візуалізують відображення інформаційних даних архітектури про наявність здатності мислення. Як навчання використовують процес машинного навчання. Інформаційні дані джерел інтернет-речей або агреговані та згруповані знання за допомогою системи розміщують на вершині вектора, а їх причинно-наслідкові зв'язки розташовують у просторі до певного часу, коли для маніпуляцій інформацією чи знаннями продукують щоразу новий онтологічний образ, який будують через адитивний ефект флуктуації образів з подовженням межі корисності, за допомогою командного процесора й вершинного шейдера. Крім цього, вершина вектора містить комбінаторику даних про кількість, різницю та їх різновид, з наступною перевіркою надативного ефекту та ергодичності системи. Також фокусують на вершині вектора ефект, принципи та суть рішень на основі латентної сингулярності евристики, яку виявляють за допомогою співставлення тотожних векторів.The way the complex decision-making system uses artificial intelligence involves the procedure of learning and forming a vector (signal) in the form of a code sequence, which is a decision-making system. The system visualizes the display of information information of the architecture of the ability to think. Machine learning is used as learning. The information sources of Internet of Things or aggregated and grouped knowledge are placed on top of the vector with the help of a system, and their cause and effect relationships are placed in space until a certain time when for manipulation of information or knowledge they produce every new ontological image, which is built through additive the effect of fluctuating images with the extension of utility, using a command processor and a vertex shader. In addition, the top of the vector contains a combination of data on the number, difference and their variant, with subsequent verification of the additive effect and ergodicity of the system. They also focus on the top of the vector the effect, principles, and essence of the solutions based on the latent singularity of heuristics, which are revealed by comparing identical vectors.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
UAU201809705U UA132430U (en) | 2018-09-27 | 2018-09-27 | METHOD OF WORK OF THE SYSTEM OF MAKING COMPLEX DECISIONS BY ARTIFICIAL INTELLIGENCE |
PCT/UA2019/000030 WO2020068025A1 (en) | 2018-09-27 | 2019-03-11 | A method of operating a system for making difficult decisions using artificial intelligence means |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
UAU201809705U UA132430U (en) | 2018-09-27 | 2018-09-27 | METHOD OF WORK OF THE SYSTEM OF MAKING COMPLEX DECISIONS BY ARTIFICIAL INTELLIGENCE |
Publications (1)
Publication Number | Publication Date |
---|---|
UA132430U true UA132430U (en) | 2019-02-25 |
Family
ID=65494872
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
UAU201809705U UA132430U (en) | 2018-09-27 | 2018-09-27 | METHOD OF WORK OF THE SYSTEM OF MAKING COMPLEX DECISIONS BY ARTIFICIAL INTELLIGENCE |
Country Status (2)
Country | Link |
---|---|
UA (1) | UA132430U (en) |
WO (1) | WO2020068025A1 (en) |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8290882B2 (en) * | 2008-10-09 | 2012-10-16 | Microsoft Corporation | Evaluating decision trees on a GPU |
WO2014026152A2 (en) * | 2012-08-10 | 2014-02-13 | Assurerx Health, Inc. | Systems and methods for pharmacogenomic decision support in psychiatry |
US11010674B2 (en) * | 2015-08-28 | 2021-05-18 | James D. Harlow | Axiomatic control of automorphic dynamical systems |
US20180121826A1 (en) * | 2016-10-28 | 2018-05-03 | Knowm Inc | Compositional Learning Through Decision Tree Growth Processes and A Communication Protocol |
CN110023962B (en) * | 2016-12-22 | 2024-03-12 | 英特尔公司 | Human experience with efficient transfer of robots and other autonomous machines |
-
2018
- 2018-09-27 UA UAU201809705U patent/UA132430U/en unknown
-
2019
- 2019-03-11 WO PCT/UA2019/000030 patent/WO2020068025A1/en active Application Filing
Also Published As
Publication number | Publication date |
---|---|
WO2020068025A1 (en) | 2020-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Weinshall et al. | Curriculum learning by transfer learning: Theory and experiments with deep networks | |
Wijmans et al. | Dd-ppo: Learning near-perfect pointgoal navigators from 2.5 billion frames | |
WO2023071743A1 (en) | Network model training method and apparatus, and computer-readable storage medium | |
US20190197109A1 (en) | System and methods for performing nlp related tasks using contextualized word representations | |
Khanzada et al. | Facial expression recognition with deep learning | |
EP3698283A1 (en) | Generative neural network systems for generating instruction sequences to control an agent performing a task | |
Гаранін et al. | Adaptive artificial intelligence in RPG-game on the Unity game engine | |
Baumgartl et al. | Development of a highly precise place recognition module for effective human-robot interactions in changing lighting and viewpoint conditions | |
Isa et al. | Optimizing the hyperparameter tuning of YOLOv5 for underwater detection | |
CN114303156A (en) | Video prediction using one or more neural networks | |
CN114925176B (en) | Method, system and medium for constructing intelligent multi-modal cognitive map | |
GB2611988A (en) | Anomaly detection in network topology | |
CN113762461A (en) | Training neural networks with finite data using reversible enhancement operators | |
Chen et al. | Octavius: Mitigating task interference in mllms via moe | |
UA132430U (en) | METHOD OF WORK OF THE SYSTEM OF MAKING COMPLEX DECISIONS BY ARTIFICIAL INTELLIGENCE | |
Wei et al. | Decision-making in ship collision avoidance based on cat-swarm biological algorithm | |
WO2019226033A3 (en) | Robot capable of autonomous movement by means of imitative-learning from object to be imitated, and autonomous movement method of robot | |
Hou et al. | Mobile augmented reality system for preschool education | |
Li et al. | Lifelong machine learning test | |
Wang et al. | Self-paced knowledge distillation for real-time image guided depth completion | |
Zhou et al. | Densely connected Siamese network visual tracking | |
Johansson et al. | Rule extraction with guaranteed fidelity | |
Gupta | Automating conversion of remote sensing images to human readable map images using generative AI | |
She et al. | IROS 2019 Lifelong Robotic Vision Challenge--Lifelong Object Recognition Report | |
Demetriou | Consciousness: The Force is Back |